solid-jobs-skills: Instructions file for Claude Code

CLAUDE.md

solid-jobs-skills CLAUDE.md is an instructions file for Claude Code from solid-company/solid-jobs-skills. It costs 2,411 tokens per session, scanned A, original, MIT.

A set of development instructions for solid-jobs-skills, a job-search command center built around the SOLID.Jobs public API. It explains the Go command-line tool, SQLite data store, project structure, and build rules.

In plain words
What is it for?
Use it when building, running, changing, or distributing solid-jobs-skills and its sjctl command-line tool.
Why use it?
It gives coding agents a shared map of where job-search logic belongs and how the project components fit together.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is solid-company/solid-jobs-skills's own configuration. It tells Claude Code how to work on solid-jobs-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything solid-jobs-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to solid-company/solid-jobs-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/solid-company/solid-jobs-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/solid-company/solid-jobs-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for solid-jobs-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/solid-company/solid-jobs-skills/claude-md/github.svg)](https://agentmods.dev/instructions/solid-company/solid-jobs-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/solid-company/solid-jobs-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/solid-company/solid-jobs-skills/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for solid-jobs-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/solid-company/solid-jobs-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/solid-company/solid-jobs-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,411 This file is loaded in full into every session.
When invoked 2,411 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02411 $0.02411
Opus 5.5 $0.00964 $0.00964
Sonnet 5.5 $0.00482 $0.00482
Haiku 4.5 $0.00241 $0.00241

Measured 2mo ago against content hash 718c8c96b89d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

solid-jobs-skills CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`~/.solid-jobs-skills/bin`. Idempotent (skips if version matches). Skills curl
CLAUDE.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

solid-jobs-skills

An AI job-search command center for the SOLID.Jobs public API. A Go binary (sjctl) does the deterministic work — fetching offers, caching, tracking, stats — and Claude skills add the judgment layer (search-from-language, offer evaluation, digests).

Architecture

cmd/sjctl              CLI (cobra) — thin wrapper, no business logic
internal/api           SOLID.Jobs API client (typed models, campaign param, 429 backoff)
internal/store         SQLite store — typed wrappers over the generated queries
internal/store/schema.sql   table definitions (sqlc source + runtime DDL)
internal/store/query.sql    all SQL queries (sqlc source)
internal/store/sqlcgen      GENERATED by sqlc — do not edit by hand
internal/jobs          Service layer — ALL business logic lives here
internal/stats         Salary/market aggregation
.claude/skills         jobs-search, jobs-create-profile, jobs-evaluate, jobs-track, jobs-digest, jobs-interview, jobs-market
config/                profile.md template
data/                  solidjobs.db (gitignored)

Dependency rule: cmd/sjctl and any future dashboard depend on internal/jobs, never the reverse. Put logic in the service layer, not in commands. SQLite is the single source of truth for offers, profiles, tracker, evaluations, interview preps and watches.

SQL rule: no SQL is inlined in Go. All queries live in internal/store/query.sql and the schema in internal/store/schema.sql; sqlc compiles them into the typed sqlcgen package. The store package wraps those generated methods. To change the database layer: edit the .sql files, run sqlc generate, then update the wrappers in internal/store/*.go.

Build & run

sqlc generate                     # regenerate internal/store/sqlcgen after editing *.sql
go build -o sjctl ./cmd/sjctl     # build the binary (sjctl.exe on Windows)
go test ./...                      # run tests
./sjctl search -d IT --term golang --remote --json

Read the full file on GitHub · 159 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 159 lines · 2,411 tokens per session scan A 718c8c96b89d

Subscribe to this mod's changes

solid-jobs-skills CLAUDE.md is an instructions file published in the GitHub repository solid-company/solid-jobs-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 2,411 tokens to every session, about $0.0096 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

solid-jobs-skills CLAUDE.md compared with instructions from other repositories

solid-jobs-skills CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
solid-jobs-skills CLAUDE.mdsolid-company/solid-jobs-skillsInstructions file52mo agoMITA2,411Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode